Skip to content

FrontierScience Research

A research-focused FrontierScience evaluation variant for scientific investigation and problem solving.

2 models

Higher is better.

  1. 1Apodex 1.1Apodex63.3
  2. 2GPT-5.4 ProOpenAI36.7
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Research evaluation
Tasks
Scientific research problems
Authors
Meta AI (2026)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.